arxiv
PublishedSeptember 21, 2026 at 4:00 AM
—neutral
Data Attribution via Sketched Metadifferentiation
Publisher summary· verbatim
arXiv:2609.15044v2 Announce Type: replace-cross Abstract: Data attribution seeks to quantify how individual training examples shape a model's predictions and underpins problems including data valuation, machine unlearning, and model interpretability. Despite having a long line of work, computational
Stay posted· Newsletter
A 5-min weekly brief — top movers, price watch, story of the week.
Discussion
No replies yet. Be first.
Related coverage
More from ARXIV
arxivLoRA Enhanced Contrastive Learning with SAS Vision Transformers6harxivHallucination-R1: Robustness-Oriented Paraphrase Generation for Factual Consistency6harxivTatBLiMP: A Benchmark of Linguistic Minimal Pairs for Tatar6harxivRuntime Authorization for Resources Acquired by AI Agents6hThe Bubble Brief
WEEKLYRead AI insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗